A
Audrunas Gruslys
Researcher at Google
Publications - 26
Citations - 3091
Audrunas Gruslys is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Image registration. The author has an hindex of 15, co-authored 25 publications receiving 2300 citations. Previous affiliations of Audrunas Gruslys include University of Cambridge.
Papers
More filters
Proceedings Article
Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward
Peter Sunehag,Guy Lever,Audrunas Gruslys,Wojciech Marian Czarnecki,Vinicius Zambaldi,Max Jaderberg,Marc Lanctot,Nicolas Sonnerat,Joel Z. Leibo,Karl Tuyls,Thore Graepel +10 more
TL;DR: This work addresses the problem of cooperative multi-agent reinforcement learning with a single joint reward signal by training individual agents with a novel value decomposition network architecture, which learns to decompose the team value function into agent-wise value functions.
Posted Content
Deep Q-learning from Demonstrations
Todd Hester,Matej Vecerík,Olivier Pietquin,Marc Lanctot,Tom Schaul,Bilal Piot,Dan Horgan,John Quan,Andrew Sendonaris,Gabriel Dulac-Arnold,Ian Osband,John P. Agapiou,Joel Z. Leibo,Audrunas Gruslys +13 more
TL;DR: Deep Q-learning from Demonstrations (DQfD) as mentioned in this paper leverages small sets of demonstration data to massively accelerate the learning process, and is able to automatically assess the necessary ratio of demonstrating data while learning thanks to a prioritized replay mechanism.
Proceedings Article
Deep Q-learning From Demonstrations.
Todd Hester,Matej Vecerík,Olivier Pietquin,Marc Lanctot,Tom Schaul,Bilal Piot,Dan Horgan,John Quan,Andrew Sendonaris,Ian Osband,Gabriel Dulac-Arnold,John P. Agapiou,Joel Z. Leibo,Audrunas Gruslys +13 more
TL;DR: Deep Q-learning from Demonstrations (DQfD) as discussed by the authors leverages small sets of demonstration data to massively accelerate the learning process, and is able to automatically assess the necessary ratio of demonstrating data while learning thanks to a prioritized replay mechanism.
Proceedings Article
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
Marc Lanctot,Vinicius Zambaldi,Audrunas Gruslys,Angeliki Lazaridou,Karl Tuyls,Julien Perolat,David Silver,Thore Graepel +7 more
TL;DR: In this article, a meta-algorithm for general MARL is proposed, based on approximate best responses to mixtures of policies generated using deep reinforcement learning, and empirical game theoretic analysis to compute meta-strategies for policy selection.
Posted Content
Value-Decomposition Networks For Cooperative Multi-Agent Learning
Peter Sunehag,Guy Lever,Audrunas Gruslys,Wojciech Marian Czarnecki,Vinicius Zambaldi,Max Jaderberg,Marc Lanctot,Nicolas Sonnerat,Joel Z. Leibo,Karl Tuyls,Thore Graepel +10 more
TL;DR: In this paper, a value decomposition network is proposed to decompose the team value function into agent-wise value functions, which leads to superior results when combined with weight sharing, role information and information channels.